Pengfei Zhang

Wenhui Ren, Weikang Li, Shibo Xu et al. · tsinghua

Quantum computing promises to enhance machine learning and artificial intelligence. Different quantum algorithms have been proposed to improve a wide spectrum of machine learning tasks. Yet, recent theoretical works show that, similar to traditional classifiers based on deep classical neural networks, quantum classifiers would suffer from the vulnerability problem: adding tiny carefully-crafted perturbations to the legitimate original data samples would facilitate incorrect predictions at a notably high confidence level. This will pose serious problems for future quantum machine learning applications in safety and security-critical scenarios. Here, we report the first experimental demonstration of quantum adversarial learning with programmable superconducting qubits. We train quantum classifiers, which are built upon variational quantum circuits consisting of ten transmon qubits featuring average lifetimes of 150 $μ$s, and average fidelities of simultaneous single- and two-qubit gates above 99.94% and 99.4% respectively, with both real-life images (e.g., medical magnetic resonance imaging scans) and quantum data. We demonstrate that these well-trained classifiers (with testing accuracy up to 99%) can be practically deceived by small adversarial perturbations, whereas an adversarial training process would significantly enhance their robustness to such perturbations. Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.

Zhi Chen, Pengfei Zhang, Jingjing Li et al.

Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizing the knowledge, i.e., visual and semantic relationships, obtained from seen classes, where image augmentation techniques are commonly applied to improve the generalization ability of a model. However, this approach can also cause adverse effects on ZSL since the conventional augmentation techniques that solely depend on single-label supervision is not able to maintain semantic information and result in the semantic distortion issue consequently. In other words, image argumentation may falsify the semantic (e.g., attribute) information of an image. To take the advantage of image augmentations while mitigating the semantic distortion issue, we propose a novel ZSL approach by Harnessing Adversarial Samples (HAS). HAS advances ZSL through adversarial training which takes into account three crucial aspects: (1) robust generation by enforcing augmentations to be similar to negative classes, while maintaining correct labels, (2) reliable generation by introducing a latent space constraint to avert significant deviations from the original data manifold, and (3) diverse generation by incorporating attribute-based perturbation by adjusting images according to each semantic attribute's localization. Through comprehensive experiments on three prominent zero-shot benchmark datasets, we demonstrate the effectiveness of our adversarial samples approach in both ZSL and Generalized Zero-Shot Learning (GZSL) scenarios. Our source code is available at https://github.com/uqzhichen/HASZSL.

Alejandro Lozano, Keiko Ihara, Ping-Hao Yang et al.

Summarizing the latest medical literature to guide clinical decision-making is essential for evidence-based medicine and high-quality patient care. Yet clinicians face increasing challenges due to limited time with patients and a rapidly growing volume of published articles. Although retrieval-augmented large language models (LLMs) have shown promise in clinical summarization, human evaluations of their effectiveness in synthesizing broader scientific literature and direct comparisons to expert-written syntheses remain scarce. We constructed a RAG-based agentic AI framework using three state-of-the-art LLMs: Sonnet, GPT-4o, and Llama 3.1. A headache specialist created 13 questions, three for prompt optimization and ten for evaluation. Ten headache specialists across the United States and Canada each wrote a summary for one question, yielding four summaries per question (expert, Sonnet, GPT-4o, and Llama). The experts, blinded to authorship, critically evaluated the summaries, excluding the topic for which they wrote a summary, based on correctness, completeness, conciseness, and clinical utility, scoring each from 1 to 10 using standardized rubrics. They also ranked the summaries by preference and indicated whether they believed each summary was written by an expert or an LLM. Our study, comparing LLM- and expert-written literature summaries evaluated by headache specialists, showed that expert-written summaries were preferred, although experts sometimes found it challenging to distinguish between human- and AI-generated summaries. We also identified key expert-valued features beyond standard evaluation metrics that can guide future refinement of both human and AI literature summarization pipelines.

Hongyu Lu, Feng Zhang, Wenwei Jin et al.

Large vision-language models (LVLMs) achieve strong performance on image and video understanding tasks, but their inference efficiency is constrained by the large number of visual tokens produced by vision encoders. Most existing visual token compression methods estimate token importance from attention scores or representation properties at specific layers, overlooking how visual tokens evolve across the vision encoder. Such layer-specific criteria may provide incomplete importance estimates and limit performance preservation after compression. To address this issue, we analyze layer-wise visual token evolution directions and observe that tokens form multiple group evolution directions across vision-encoder layers. Our analysis further shows that informative tokens tend to exhibit persistent deviations from common group evolution directions. Based on this observation, we propose EvoCut, a training-free and attention-free visual token compression method that estimates token importance from multi-layer evolution deviation. Experimental results show that EvoCut can retain only 11.1\% of the visual tokens on LLaVA-1.5-7B while preserving 94.4\% of the average performance, demonstrating its effectiveness in balancing efficiency and accuracy.

He Wang, Jun Feng, Hong Sun et al.

Current backdoor attacks against LLMs are typically manipulated by the attacker and remain passive. In this paper, we introduce the \textbf{Proactive Availability Backdoor (PAB)}, a novel paradigm that shifts the attack vector from passive waiting to active social engineering. By weaponizing the inherent helpfulness of aligned LLMs, PAB proactively traps users into executing trigger-implanted queries by offering suggestions, achieving high aggressiveness, precision and stealthiness. To rigorously evaluate its threat in a real-life context, we introduce a dual-agent ecological simulation framework based on selected dimensions of the Five-Factor Model, and deploy PAB with few-shot prompts. Being validated on different models and domains, PAB performs remarkably and its effective attack success rate, which calculates the joint probability of attack incidence rate and attack success rate, goes to \textbf{73.1\%}. We also introduce \textbf{Anti-PAB}, a defense method tailored for PAB. Our findings reveal that the helpfulness of LLMs can be weaponized to compromise availability, exposing a serious hidden threat to LLMs users. We release all the scripts and datasets in the experiments at \texttt{https://anonymous.4open.science/r/PAB-ANONYMOUS/}.

Chaoran Xu, Yingmao Miao, Pengfei Zhang et al.

Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision for post-training. Such supervision is costly to obtain, especially for reasoning-intensive multimodal tasks where questions, answers, and feedback signals must be carefully designed. This motivates self-evolving learning, where a model improves itself through a dual-role closed loop: a questioner autonomously poses questions and a solver learns to solve them. However, we observe that current VLM self-evolving methods still face three major challenges: coarse-grained role alternation delays the interaction between question generation and solver adaptation; generated questions can progressively degrade in quality; and question types may collapse toward a narrow distribution. These issues limit the efficiency and reliability of self-evolution. Thus, we propose \textbf{RISE}, a reliable self-evolving framework for vision-language models. RISE is built on three complementary designs: fine-grained role alternation, which shortens the feedback loop between the questioner and the solver to improve efficiency; a quality supervisor, which improves question validity and pseudo-label reliability; and skill-aware dynamic balancing, which mitigates mode collapse and maintains broad skill coverage during evolution. Together, these components enable more reliable and effective self-evolution from unlabeled images. Experiments on two VLM backbones across seven benchmarks show that RISE consistently improves the base models, yielding broad and sustained gains. Our code is publicly available at https://github.com/AMAP-ML/RISE.

Yibiao Wei, Jie Zou, Pengfei Zhang et al.

Generative recommendation frameworks typically represent items as discrete Semantic IDs (SIDs). While existing studies have sought to enhance SID construction by incorporating multimodal content, collaborative signals, or more advanced quantization techniques, learning high-quality SIDs still faces two key challenges: (1) The two-stage generative recommendation paradigm (SID construction and autoregressive generation) provides insufficient supervision for heterogeneous fusion, which hinders learning high-quality SIDs, and (2) non-uniform embeddings lead to codeword imbalance and generation bias. To address these challenges, we propose a novel generative recommendation framework, called CARD. CARD introduces a visual semantic unit that unifies textual, visual, and collaborative signals into a structured visual representation prior to encoding, enabling holistic semantic modeling and effectively alleviating the semantic gap, thereby reducing the reliance on supervision signals during SID learning. Furthermore, to deal with the highly non-uniform distribution of item semantic embeddings in recommendation scenarios, we develop a non-uniform quantization framework (NU-RQ-VAE), which incorporates a learnable and invertible non-uniform transformation into the quantization process to map skewed semantic distributions into a more balanced latent space, thereby significantly improving codebook utilization and quantization accuracy. Experiments on multiple datasets show that CARD consistently outperforms baseline methods under various settings; meanwhile, the proposed non-uniform transformation module is plug-and-play and remains robust across different quantization schemes. Code is available at https://github.com/HAI-UESTC/CARD.

Mahyar Abbasian, Zhongqi Yang, Elahe Khatibi et al.

Effective diabetes management is crucial for maintaining health in diabetic patients. Large Language Models (LLMs) have opened new avenues for diabetes management, facilitating their efficacy. However, current LLM-based approaches are limited by their dependence on general sources and lack of integration with domain-specific knowledge, leading to inaccurate responses. In this paper, we propose a knowledge-infused LLM-powered conversational health agent (CHA) for diabetic patients. We customize and leverage the open-source openCHA framework, enhancing our CHA with external knowledge and analytical capabilities. This integration involves two key components: 1) incorporating the American Diabetes Association dietary guidelines and the Nutritionix information and 2) deploying analytical tools that enable nutritional intake calculation and comparison with the guidelines. We compare the proposed CHA with GPT4. Our evaluation includes 100 diabetes-related questions on daily meal choices and assessing the potential risks associated with the suggested diet. Our findings show that the proposed agent demonstrates superior performance in generating responses to manage essential nutrients.

Pengfei Zhang, Xiaohui Hu, Kaidong Yu et al.

Automatic open-domain dialogue evaluation is a crucial component of dialogue systems. Recently, learning-based evaluation metrics have achieved state-of-the-art performance in open-domain dialogue evaluation. However, these metrics, which only focus on a few qualities, are hard to evaluate dialogue comprehensively. Furthermore, these metrics lack an effective score composition approach for diverse evaluation qualities. To address the above problems, we propose a Multi-Metric Evaluation based on Correlation Re-Scaling (MME-CRS) for evaluating open-domain dialogue. Firstly, we build an evaluation metric composed of 5 groups of parallel sub-metrics called Multi-Metric Evaluation (MME) to evaluate the quality of dialogue comprehensively. Furthermore, we propose a novel score composition method called Correlation Re-Scaling (CRS) to model the relationship between sub-metrics and diverse qualities. Our approach MME-CRS ranks first on the final test data of DSTC10 track5 subtask1 Automatic Open-domain Dialogue Evaluation Challenge with a large margin, which proved the effectiveness of our proposed approach.

Wenyu Liu, Tianqiang Huang, Pengfei Zhang et al.

Adversarial attacks pose a major challenge to distributed learning systems, prompting the development of numerous robust learning methods. However, most existing approaches suffer from the curse of dimensionality, i.e. the error increases with the number of model parameters. In this paper, we make a progress towards high dimensional problems, under arbitrary number of Byzantine attackers. The cornerstone of our design is a direct high dimensional semi-verified mean estimation method. The idea is to identify a subspace with large variance. The components of the mean value perpendicular to this subspace are estimated using corrupted gradient vectors uploaded from worker machines, while the components within this subspace are estimated using auxiliary dataset. As a result, a combination of large corrupted dataset and small clean dataset yields significantly better performance than using them separately. We then apply this method as the aggregator for distributed learning problems. The theoretical analysis shows that compared with existing solutions, our method gets rid of $\sqrt{d}$ dependence on the dimensionality, and achieves minimax optimal statistical rates. Numerical results validate our theory as well as the effectiveness of the proposed method.

Ben Xue, Dan Liu, Lixiang Wang et al.

Generative recommendation has recently attracted widespread attention in industry due to its potential for scaling and stronger model capacity. However, deploying real-time generative recommendation in large-scale advertising requires designs beyond large-language-model (LLM)-style training and serving recipes. We present a production-oriented generative recommender co-designed across architecture, learning, and serving, named GR4AD (Generative Recommendation for ADdvertising). As for tokenization, GR4AD proposes UA-SID (Unified Advertisement Semantic ID) to capture complicated business information. Furthermore, GR4AD introduces LazyAR, a lazy autoregressive decoder that relaxes layer-wise dependencies for short, multi-candidate generation, preserving effectiveness while reducing inference cost, which facilitates scaling under fixed serving budgets. To align optimization with business value, GR4AD employs VSL (Value-Aware Supervised Learning) and proposes RSPO (Ranking-Guided Softmax Preference Optimization), a ranking-aware, list-wise reinforcement learning algorithm that optimizes value-based rewards under list-level metrics for continual online updates. For online inference, we further propose dynamic beam serving, which adapts beam width across generation levels and online load to control compute. Large-scale online A/B tests show up to 4.2% ad revenue improvement over an existing DLRM-based stack, with consistent gains from both model scaling and inference-time scaling. GR4AD has been fully deployed in Kuaishou advertising system with over 400 million users and achieves high-throughput real-time serving.

Pengfei Zhang, Tingting Chai, Yongdong Xu

In the field of natural language processing, sentiment analysis via deep learning has a excellent performance by using large labeled datasets. Meanwhile, labeled data are insufficient in many sentiment analysis, and obtaining these data is time-consuming and laborious. Prompt learning devotes to resolving the data deficiency by reformulating downstream tasks with the help of prompt. In this way, the appropriate prompt is very important for the performance of the model. This paper proposes an adaptive prompting(AP) construction strategy using seq2seq-attention structure to acquire the semantic information of the input sequence. Then dynamically construct adaptive prompt which can not only improve the quality of the prompt, but also can effectively generalize to other fields by pre-trained prompt which is constructed by existing public labeled data. The experimental results on FewCLUE datasets demonstrate that the proposed method AP can effectively construct appropriate adaptive prompt regardless of the quality of hand-crafted prompt and outperform the state-of-the-art baselines.

Zhiyi Zhang, Pengfei Zhang, Zhuopin Xu et al.

Convolutional neural networks necessitate good algorithms to reduce complexity, and sufficient utilization of parallel processors for acceleration. Within convolutional layers, there are three types of operators: convolution used in forward propagation, deconvolution and dilated-convolution utilized in backward propagation. During the execution of these operators, zeros are typically added to tensors, leading to redundant calculations and unnecessary strain on hardware. To circumvent these inefficiencies, we propose the C-K-S algorithm, accompanied by efficient GPU implementations. C-K-S trims filters to exclude zero-padding. For deconvolution and dilated-convolution, C-K-S transforms sparse tensors into dense tensors, and standardizes the local computational rules to simplify the hardware control. The experimental results demonstrate that C-K-S offers good performance in terms of speed and convergence, surpassing the capabilities of PyTorch and cuDNN in certain scenarios.

Yu Zhang, Mufan Xu, Xuefeng Bai et al.

Modality following serves as the capacity of multimodal large language models (MLLMs) to selectively utilize multimodal contexts based on user instructions. It is fundamental to ensuring safety and reliability in real-world deployments. However, the underlying mechanisms governing this decision-making process remain poorly understood. In this paper, we investigate its working mechanism through an information flow lens. Our findings reveal that instruction tokens function as structural anchors for modality arbitration: Shallow attention layers perform non-selective information transfer, routing multimodal cues to these anchors as a latent buffer; Modality competition is resolved within deep attention layers guided by the instruction intent, while MLP layers exhibit semantic inertia, acting as an adversarial force. Furthermore, we identify a sparse set of specialized attention heads that drive this arbitration. Causal interventions demonstrate that manipulating a mere $5\%$ of these critical heads can decrease the modality-following ratio by $60\%$ through blocking, or increase it by $60\%$ through targeted amplification of failed samples. Our work provides a substantial step toward model transparency and offers a principled framework for the orchestration of multimodal information in MLLMs.

Tianxin Xie, Yan Rong, Pengfei Zhang et al.

Text-to-speech (TTS) has advanced from generating natural-sounding speech to enabling fine-grained control over attributes like emotion, timbre, and style. Driven by rising industrial demand and breakthroughs in deep learning, e.g., diffusion and large language models (LLMs), controllable TTS has become a rapidly growing research area. This survey provides the first comprehensive review of controllable TTS methods, from traditional control techniques to emerging approaches using natural language prompts. We categorize model architectures, control strategies, and feature representations, while also summarizing challenges, datasets, and evaluations in controllable TTS. This survey aims to guide researchers and practitioners by offering a clear taxonomy and highlighting future directions in this fast-evolving field. One can visit https://github.com/imxtx/awesome-controllabe-speech-synthesis for a comprehensive paper list and updates.

Pengfei Zhang, Zhihang Zheng, Shichen Zhang et al.

Compared with invasive examinations that require tissue sampling, respiratory sound testing is a non-invasive examination method that is safer and easier for patients to accept. In this study, we introduce Rene, a pioneering large-scale model tailored for respiratory sound recognition. Rene has been rigorously fine-tuned with an extensive dataset featuring a broad array of respiratory audio samples, targeting disease detection, sound pattern classification, and event identification. Our innovative approach applies a pre-trained speech recognition model to process respiratory sounds, augmented with patient medical records. The resulting multi-modal deep-learning framework addresses interpretability and real-time diagnostic challenges that have hindered previous respiratory-focused models. Benchmark comparisons reveal that Rene significantly outperforms existing models, achieving improvements of 10.27%, 16.15%, 15.29%, and 18.90% in respiratory event detection and audio classification on the SPRSound database. Disease prediction accuracy on the ICBHI database improved by 23% over the baseline in both mean average and harmonic scores. Moreover, we have developed a real-time respiratory sound discrimination system utilizing the Rene architecture. Employing state-of-the-art Edge AI technology, this system enables rapid and accurate responses for respiratory sound auscultation(https://github.com/zpforlove/Rene).

Tianxin Xie, Wentao Lei, Guanjie Huang et al.

Text-to-audio-video (T2AV) generation underpins a wide range of applications demanding realistic audio-visual content, including virtual reality, world modeling, gaming, and filmmaking. However, existing T2AV models remain incapable of generating physically plausible sounds, primarily due to their limited understanding of physical principles. To situate current research progress, we present PhyAVBench, a challenging audio physics-sensitivity benchmark designed to systematically evaluate the audio physics grounding capabilities of existing T2AV models. PhyAVBench comprises 1,000 groups of paired text prompts with controlled physical variables that implicitly induce sound variations, enabling a fine-grained assessment of models' sensitivity to changes in underlying acoustic conditions. We term this evaluation paradigm the Audio-Physics Sensitivity Test (APST). Unlike prior benchmarks that primarily focus on audio-video synchronization, PhyAVBench explicitly evaluates models' understanding of the physical mechanisms underlying sound generation, covering 6 major audio physics dimensions, 4 daily scenarios (music, sound effects, speech, and their mix), and 50 fine-grained test points, ranging from fundamental aspects such as sound diffraction to more complex phenomena, e.g., Helmholtz resonance. Each test point consists of multiple groups of paired prompts, where each prompt is grounded by at least 20 newly recorded or collected real-world videos, thereby minimizing the risk of data leakage during model pre-training. Both prompts and videos are iteratively refined through rigorous human-involved error correction and quality control to ensure high quality. We argue that only models with a genuine grasp of audio-related physical principles can generate physically consistent audio-visual content. We hope PhyAVBench will stimulate future progress in this critical yet largely unexplored domain.

Yutong Song, Shiva Shrestha, Chenhan Lyu et al.

Spoken question-answering (SQA) systems relying on automatic speech recognition (ASR) often struggle with accurately recognizing medical terminology. To this end, we propose MedSpeak, a novel knowledge graph-aided ASR error correction framework that refines noisy transcripts and improves downstream answer prediction by leveraging both semantic relationships and phonetic information encoded in a medical knowledge graph, together with the reasoning power of LLMs. Comprehensive experimental results on benchmarks demonstrate that MedSpeak significantly improves the accuracy of medical term recognition and overall medical SQA performance, establishing MedSpeak as a state-of-the-art solution for medical SQA. The code is available at https://github.com/RainieLLM/MedSpeak.

Pengfei Zhang, Zhengyuan Jiang, Yixuan Wang et al.

The reconstruction of microbial genomes from large metagenomic datasets is a critical procedure for finding uncultivated microbial populations and defining their microbial functional roles. To achieve that, we need to perform metagenomic binning, clustering the assembled contigs into draft genomes. Despite the existing computational tools, most of them neglect one important property of the metagenomic data, that is, the noise. To further improve the metagenomic binning step and reconstruct better metagenomes, we propose a deep Contrastive Learning framework for Metagenome Binning (CLMB), which can efficiently eliminate the disturbance of noise and produce more stable and robust results. Essentially, instead of denoising the data explicitly, we add simulated noise to the training data and force the deep learning model to produce similar and stable representations for both the noise-free data and the distorted data. Consequently, the trained model will be robust to noise and handle it implicitly during usage. CLMB outperforms the previous state-of-the-art binning methods significantly, recovering the most near-complete genomes on almost all the benchmarking datasets (up to 17\% more reconstructed genomes compared to the second-best method). It also improves the performance of bin refinement, reconstructing 8-22 more high-quality genomes and 15-32 more middle-quality genomes than the second-best result. Impressively, in addition to being compatible with the binning refiner, single CLMB even recovers on average 15 more HQ genomes than the refiner of VAMB and Maxbin on the benchmarking datasets. CLMB is open-source and available at https://github.com/zpf0117b/CLMB/.

Qingzhong Wang, Pengfei Zhang, Haoyi Xiong et al.

In this paper, we develop face.evoLVe -- a comprehensive library that collects and implements a wide range of popular deep learning-based methods for face recognition. First of all, face.evoLVe is composed of key components that cover the full process of face analytics, including face alignment, data processing, various backbones, losses, and alternatives with bags of tricks for improving performance. Later, face.evoLVe supports multi-GPU training on top of different deep learning platforms, such as PyTorch and PaddlePaddle, which facilitates researchers to work on both large-scale datasets with millions of images and low-shot counterparts with limited well-annotated data. More importantly, along with face.evoLVe, images before & after alignment in the common benchmark datasets are released with source codes and trained models provided. All these efforts lower the technical burdens in reproducing the existing methods for comparison, while users of our library could focus on developing advanced approaches more efficiently. Last but not least, face.evoLVe is well designed and vibrantly evolving, so that new face recognition approaches can be easily plugged into our framework. Note that we have used face.evoLVe to participate in a number of face recognition competitions and secured the first place. The version that supports PyTorch is publicly available at https://github.com/ZhaoJ9014/face.evoLVe.PyTorch and the PaddlePaddle version is available at https://github.com/ZhaoJ9014/face.evoLVe.PyTorch/tree/master/paddle. Face.evoLVe has been widely used for face analytics, receiving 2.4K stars and 622 forks.

Pengfei Zhang, Cuiling Lan, Wenjun Zeng et al.

Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data. Recently, there is a trend of using very deep feedforward neural networks to model the 3D coordinates of joints without considering the computational efficiency. In this paper, we propose a simple yet effective semantics-guided neural network (SGN) for skeleton-based action recognition. We explicitly introduce the high level semantics of joints (joint type and frame index) into the network to enhance the feature representation capability. In addition, we exploit the relationship of joints hierarchically through two modules, i.e., a joint-level module for modeling the correlations of joints in the same frame and a framelevel module for modeling the dependencies of frames by taking the joints in the same frame as a whole. A strong baseline is proposed to facilitate the study of this field. With an order of magnitude smaller model size than most previous works, SGN achieves the state-of-the-art performance on the NTU60, NTU120, and SYSU datasets. The source code is available at https://github.com/microsoft/SGN.

Pengfei Zhang, Cuiling Lan, Junliang Xing et al.

Skeleton-based human action recognition has recently attracted increasing attention thanks to the accessibility and the popularity of 3D skeleton data. One of the key challenges in skeleton-based action recognition lies in the large view variations when capturing data. In order to alleviate the effects of view variations, this paper introduces a novel view adaptation scheme, which automatically determines the virtual observation viewpoints in a learning based data driven manner. We design two view adaptive neural networks, i.e., VA-RNN based on RNN, and VA-CNN based on CNN. For each network, a novel view adaptation module learns and determines the most suitable observation viewpoints, and transforms the skeletons to those viewpoints for the end-to-end recognition with a main classification network. Ablation studies find that the proposed view adaptive models are capable of transforming the skeletons of various viewpoints to much more consistent virtual viewpoints which largely eliminates the viewpoint influence. In addition, we design a two-stream scheme (referred to as VA-fusion) that fuses the scores of the two networks to provide the fused prediction. Extensive experimental evaluations on five challenging benchmarks demonstrate that the effectiveness of the proposed view-adaptive networks and superior performance over state-of-the-art approaches. The source code is available at https://github.com/microsoft/View-Adaptive-Neural-Networks-for-Skeleton-based-Human-Action-Recognition.

Pengfei Zhang, Tianxin Xie, Minghao Yang et al.

REPresentation Alignment (REPA) improves the training of generative flow models by aligning intermediate hidden states with pretrained teacher features, but its effectiveness in token-conditioned audio Flow Matching critically depends on the choice of supervised layers, which is typically made heuristically based on the depth. In this work, we introduce Attribution-Guided REPresentation Alignment (AG-REPA), a novel causal layer selection strategy for representation alignment in audio Flow Matching. Firstly, we find that layers that best store semantic/acoustic information (high teacher-space similarity) are not necessarily the layers that contribute most to the velocity field that drives generation, and we call it Store-Contribute Dissociation (SCD). To turn this insight into an actionable training guidance, we propose a forward-only gate ablation (FoG-A) that quantifies each layer's causal contribution via the induced change in the predicted velocity field, enabling sparse layer selection and adaptive weighting for alignment. Across unified speech and general-audio training (LibriSpeech + AudioSet) under different token-conditioning topologies, AG-REPA consistently outperforms REPA baselines. Overall, our results show that alignment is most effective when applied to the causally dominant layers that drive the velocity field, rather than to layers that are representationally rich but functionally passive.

Zeyu Chen, Pengfei Zhang, Kai Ye et al.

The burgeoning short video industry has accelerated the advancement of video-music retrieval technology, assisting content creators in selecting appropriate music for their videos. In self-supervised training for video-to-music retrieval, the video and music samples in the dataset are separated from the same video work, so they are all one-to-one matches. This does not match the real situation. In reality, a video can use different music as background music, and a music can be used as background music for different videos. Many videos and music that are not in a pair may be compatible, leading to false negative noise in the dataset. A novel inter-intra modal (II) loss is proposed as a solution. By reducing the variation of feature distribution within the two modalities before and after the encoder, II loss can reduce the model's overfitting to such noise without removing it in a costly and laborious way. The video-music retrieval framework, II-CLVM (Contrastive Learning for Video-Music Retrieval), incorporating the II Loss, achieves state-of-the-art performance on the YouTube8M dataset. The framework II-CLVTM shows better performance when retrieving music using multi-modal video information (such as text in videos). Experiments are designed to show that II loss can effectively alleviate the problem of false negative noise in retrieval tasks. Experiments also show that II loss improves various self-supervised and supervised uni-modal and cross-modal retrieval tasks, and can obtain good retrieval models with a small amount of training samples.

Pengfei Zhang, Seojin Bang, Heewook Lee

T cell receptors (TCRs) are critical components of adaptive immune systems, responsible for responding to threats by recognizing epitope sequences presented on host cell surface. Computational prediction of binding affinity between TCRs and epitope sequences using machine/deep learning has attracted intense attention recently. However, its success is hindered by the lack of large collections of annotated TCR-epitope pairs. Annotating their binding affinity requires expensive and time-consuming wet-lab evaluation. To reduce annotation cost, we present ActiveTCR, a framework that incorporates active learning and TCR-epitope binding affinity prediction models. Starting with a small set of labeled training pairs, ActiveTCR iteratively searches for unlabeled TCR-epitope pairs that are ''worth'' for annotation. It aims to maximize performance gains while minimizing the cost of annotation. We compared four query strategies with a random sampling baseline and demonstrated that ActiveTCR reduces annotation costs by approximately 40%. Furthermore, we showed that providing ground truth labels of TCR-epitope pairs to query strategies can help identify and reduce more than 40% redundancy among already annotated pairs without compromising model performance, enabling users to train equally powerful prediction models with less training data. Our work is the first systematic investigation of data optimization for TCR-epitope binding affinity prediction.

Pengfei Zhang, Dingzhu Wen, Guangxu Zhu et al.

In this paper, a cloud radio access network (Cloud-RAN) based collaborative edge AI inference architecture is proposed. Specifically, geographically distributed devices capture real-time noise-corrupted sensory data samples and extract the noisy local feature vectors, which are then aggregated at each remote radio head (RRH) to suppress sensing noise. To realize efficient uplink feature aggregation, we allow each RRH receives local feature vectors from all devices over the same resource blocks simultaneously by leveraging an over-the-air computation (AirComp) technique. Thereafter, these aggregated feature vectors are quantized and transmitted to a central processor (CP) for further aggregation and downstream inference tasks. Our aim in this work is to maximize the inference accuracy via a surrogate accuracy metric called discriminant gain, which measures the discernibility of different classes in the feature space. The key challenges lie on simultaneously suppressing the coupled sensing noise, AirComp distortion caused by hostile wireless channels, and the quantization error resulting from the limited capacity of fronthaul links. To address these challenges, this work proposes a joint transmit precoding, receive beamforming, and quantization error control scheme to enhance the inference accuracy. Extensive numerical experiments demonstrate the effectiveness and superiority of our proposed optimization algorithm compared to various baselines.

Pinxin Liu, Pengfei Zhang, Hyeongwoo Kim et al.

Co-speech gesture generation is crucial for creating lifelike avatars and enhancing human-computer interactions by synchronizing gestures with speech. Despite recent advancements, existing methods struggle with accurately identifying the rhythmic or semantic triggers from audio for generating contextualized gesture patterns and achieving pixel-level realism. To address these challenges, we introduce Contextual Gesture, a framework that improves co-speech gesture video generation through three innovative components: (1) a chronological speech-gesture alignment that temporally connects two modalities, (2) a contextualized gesture tokenization that incorporate speech context into motion pattern representation through distillation, and (3) a structure-aware refinement module that employs edge connection to link gesture keypoints to improve video generation. Our extensive experiments demonstrate that Contextual Gesture not only produces realistic and speech-aligned gesture videos but also supports long-sequence generation and video gesture editing applications, shown in Fig.1.

Chang Li, Pengfei Zhang, Yu Wang

Currently the semantic segmentation task of multispectral remotely sensed imagery (MSRSI) faces the following problems: 1) Usually, only single domain feature (i.e., space domain or frequency domain) is considered; 2) downsampling operation in encoder generally leads to the accuracy loss of edge extraction; 3) multichannel features of MSRSI are not fully considered; and 4) prior knowledge of remote sensing is not fully utilized. To solve the aforementioned issues, an index-space-wave state superposition Transformer (ISWSST) is the first to be proposed for MSRSI semantic segmentation by the inspiration from quantum mechanics, whose superiority is as follows: 1) index, space and wave states are superposed or fused to simulate quantum superposition by adaptively voting decision (i.e., ensemble learning idea) for being a stronger classifier and improving the segmentation accuracy; 2) a lossless wavelet pyramid encoder-decoder module is designed to losslessly reconstruct image and simulate quantum entanglement based on wavelet transform and inverse wavelet transform for avoiding the edge extraction loss; 3) combining multispectral features (i.e. remote sensing index and channel attention mechanism) is proposed to accurately extract ground objects from original resolution images; and 4) quantum mechanics are introduced to interpret the underlying superiority of ISWSST. Experiments show that ISWSST is validated and superior to the state-of-the-art architectures for the MSRSI segmentation task, which improves the segmentation and edge extraction accuracy effectively. Codes will be available publicly after our paper is accepted.

Pengfei Zhang, Pinxin Liu, Pablo Garrido et al.

Current human motion synthesis frameworks rely on global action descriptions, creating a modality gap that limits both motion understanding and generation capabilities. A single coarse description, such as run, fails to capture details such as variations in speed, limb positioning, and kinematic dynamics, leading to ambiguities between text and motion modalities. To address this challenge, we introduce KinMo, a unified framework built on a hierarchical describable motion representation that extends beyond global actions by incorporating kinematic group movements and their interactions. We design an automated annotation pipeline to generate high-quality, fine-grained descriptions for this decomposition, resulting in the KinMo dataset and offering a scalable and cost-efficient solution for dataset enrichment. To leverage these structured descriptions, we propose Hierarchical Text-Motion Alignment that progressively integrates additional motion details, thereby improving semantic motion understanding. Furthermore, we introduce a coarse-to-fine motion generation procedure to leverage enhanced spatial understanding to improve motion synthesis. Experimental results show that KinMo significantly improves motion understanding, demonstrated by enhanced text-motion retrieval performance and enabling more fine-grained motion generation and editing capabilities. Project Page: https://andypinxinliu.github.io/KinMo

Yutong Song, Chenhan Lyu, Pengfei Zhang et al.

Mild-stage dementia patients primarily experience two critical symptoms: severe memory loss and emotional instability. To address these challenges, we propose DEMENTIA-PLAN, an innovative retrieval-augmented generation framework that leverages large language models to enhance conversational support. Our model employs a multiple knowledge graph architecture, integrating various dimensional knowledge representations including daily routine graphs and life memory graphs. Through this multi-graph architecture, DEMENTIA-PLAN comprehensively addresses both immediate care needs and facilitates deeper emotional resonance through personal memories, helping stabilize patient mood while providing reliable memory support. Our notable innovation is the self-reflection planning agent, which systematically coordinates knowledge retrieval and semantic integration across multiple knowledge graphs, while scoring retrieved content from daily routine and life memory graphs to dynamically adjust their retrieval weights for optimized response generation. DEMENTIA-PLAN represents a significant advancement in the clinical application of large language models for dementia care, bridging the gap between AI tools and caregivers interventions.

Lei Zhou, Youwen Zhu, Qiao Xue et al.

Recently, the enactment of ``right to be forgotten" laws and regulations has imposed new privacy requirements on federated learning (FL). Researchers aim to remove the influence of certain data from the trained model without training from scratch through federated unlearning (FU). While current FU research has shown progress in enhancing unlearning efficiency, it often results in degraded model performance upon achieving the goal of data unlearning, necessitating additional steps to recover the performance of the unlearned model. Moreover, these approaches also suffer from many shortcomings such as high consumption of computational and storage resources. To this end, we propose a streamlined federated unlearning approach (SFU) aimed at effectively removing the influence of the target data while preserving the model performance on the retained data without degradation. We design a practical multi-teacher system that achieves both target data influence removal and model performance preservation by guiding the unlearned model through several distinct teacher models. SFU is both computationally and storage-efficient, highly flexible, and generalizable. We conduct extensive experiments on both image and text benchmark datasets. The results demonstrate that SFU significantly improves time and communication efficiency compared to the benchmark retraining method and significantly outperforms existing SOTA methods. Additionally, we verify the effectiveness of SFU using the backdoor attack.

Li Sun, Mengjie Li, Yong Yang et al.

Link prediction typically studies the probability of future interconnection among nodes with the observation in a single social network. More often than not, real scenario is presented as a multiplex network with common (anchor) users active in multiple social networks. In the literature, most existing works study either the intra-link prediction in a single network or inter-link prediction among networks (a.k.a. network alignment), and consider two learning tasks are independent from each other, which is still away from the fact. On the representation space, the vast majority of existing methods are built upon the traditional Euclidean space, unaware of the inherent geometry of social networks. The third issue is on the scarce anchor users. Annotating anchor users is laborious and expensive, and thus it is impractical to work with quantities of anchor users. Herein, in light of the issues above, we propose to study a challenging yet practical problem of Geometry-aware Collective Link Prediction across Multiplex Network. To address this problem, we present a novel contrastive model, RCoCo, which collaborates intra- and inter-network behaviors in Riemannian spaces. In RCoCo, we design a curvature-aware graph attention network ($κ-$GAT), conducting attention mechanism in Riemannian manifold whose curvature is estimated by the Ricci curvatures over the network. Thereafter, we formulate intra- and inter-contrastive loss in the manifolds, in which we augment graphs by exploring the high-order structure of community and information transfer on anchor users. Finally, we conduct extensive experiments with 14 strong baselines on 8 real-world datasets, and show the effectiveness of RCoCo.

Yongchao Huang, Pengfei Zhang, Shahzad Mumtaz

Membership inference attacks (MIAs) test whether a data point was part of a model's training set, posing serious privacy risks. Existing methods often depend on shadow models or heavy query access, which limits their practicality. We propose GP-MIA, an efficient and interpretable approach based on Gaussian process (GP) meta-modeling. Using post-hoc metrics such as accuracy, entropy, dataset statistics, and optional sensitivity features (e.g. gradients, NTK measures) from a single trained model, GP-MIA trains a GP classifier to distinguish members from non-members while providing calibrated uncertainty estimates. Experiments on synthetic data, real-world fraud detection data, CIFAR-10, and WikiText-2 show that GP-MIA achieves high accuracy and generalizability, offering a practical alternative to existing MIAs.

Chenhan Lyu, Yutong Song, Pengfei Zhang et al.

Mental health applications have emerged as a critical area in computational health, driven by rising global rates of mental illness, the integration of AI in psychological care, and the need for scalable solutions in underserved communities. These include therapy chatbots, crisis detection, and wellness platforms handling sensitive data, requiring specialized AI safety beyond general safeguards due to emotional vulnerability, risks like misdiagnosis or symptom exacerbation, and precise management of vulnerable states to avoid severe outcomes such as self-harm or loss of trust. Despite AI safety advances, general safeguards inadequately address mental health-specific challenges, including crisis intervention accuracy to avert escalations, therapeutic guideline adherence to prevent misinformation, scale limitations in resource-constrained settings, and adaptation to nuanced dialogues where generics may introduce biases or miss distress signals. We introduce an approach to apply Constitutional AI training with domain-specific mental health principles for safe, domain-adapted CAI systems in computational mental health applications.

Pengfei Zhang, Shouqing Jia

Denoising Diffusion Probabilistic Models (DDPM) process images as a whole. Since adjacent pixels are highly likely to belong to the same object, we propose the Heat Diffusion Model (HDM) to further preserve image details and generate more realistic images. HDM essentially is a DDPM that incorporates an attention mechanism between pixels. In HDM, the discrete form of the two-dimensional heat equation is integrated into the diffusion and generation formulas of DDPM, enabling the model to compute relationships between neighboring pixels during image processing. Our experiments demonstrate that HDM can generate higher-quality samples compared to models such as DDPM, Consistency Diffusion Models (CDM), Latent Diffusion Models (LDM), and Vector Quantized Generative Adversarial Networks (VQGAN).

Minghao Yang, Pengteng Li, Yan Liang et al.

Deep learning techniques have driven significant progress in various analytical tasks within 3D genomics in computational biology. However, a holistic understanding of 3D genomics knowledge remains underexplored. Here, we propose MIX-HIC, the first multimodal foundation model of 3D genome that integrates both 3D genome structure and epigenomic tracks, which obtains unified and comprehensive semantics. For accurate heterogeneous semantic fusion, we design the cross-modal interaction and mapping blocks for robust unified representation, yielding the accurate aggregation of 3D genome knowledge. Besides, we introduce the first large-scale dataset comprising over 1 million pairwise samples of Hi-C contact maps and epigenomic tracks for high-quality pre-training, enabling the exploration of functional implications in 3D genomics. Extensive experiments show that MIX-HIC can significantly surpass existing state-of-the-art methods in diverse downstream tasks. This work provides a valuable resource for advancing 3D genomics research.

Minghao Yang, Zhi-An Huang, Zhihang Zheng et al.

Hi-C technology measures genome-wide interaction frequencies, providing a powerful tool for studying the 3D genomic structure within the nucleus. However, high sequencing costs and technical challenges often result in Hi-C data with limited coverage, leading to imprecise estimates of chromatin interaction frequencies. To address this issue, we present a novel deep learning-based method HiCMamba to enhance the resolution of Hi-C contact maps using a state space model. We adopt the UNet-based auto-encoder architecture to stack the proposed holistic scan block, enabling the perception of both global and local receptive fields at multiple scales. Experimental results demonstrate that HiCMamba outperforms state-of-the-art methods while significantly reducing computational resources. Furthermore, the 3D genome structures, including topologically associating domains (TADs) and loops, identified in the contact maps recovered by HiCMamba are validated through associated epigenomic features. Our work demonstrates the potential of a state space model as foundational frameworks in the field of Hi-C resolution enhancement.

Jiakai Wang, Pengfei Zhang, Renshuai Tao et al.

The various post-processing methods for deep-learning-based models, such as quantification, pruning, and fine-tuning, play an increasingly important role in artificial intelligence technology, with pre-train large models as one of the main development directions. However, this popular series of post-processing behaviors targeting pre-training deep models has become a breeding ground for new adversarial security issues. In this study, we take the first step towards ``behavioral backdoor'' attack, which is defined as a behavior-triggered backdoor model training procedure, to reveal a new paradigm of backdoor attacks. In practice, we propose the first pipeline of implementing behavior backdoor, i.e., the Quantification Backdoor (QB) attack, upon exploiting model quantification method as the set trigger. Specifically, to adapt the optimization goal of behavior backdoor, we introduce the behavior-driven backdoor object optimizing method by a bi-target behavior backdoor training loss, thus we could guide the poisoned model optimization direction. To update the parameters across multiple models, we adopt the address-shared backdoor model training, thereby the gradient information could be utilized for multimodel collaborative optimization. Extensive experiments have been conducted on different models, datasets, and tasks, demonstrating the effectiveness of this novel backdoor attack and its potential application threats.

Ke Wang, Weikang Li, Shibo Xu et al.

Quantum nonlocality describes a stronger form of quantum correlation than that of entanglement. It refutes Einstein's belief of local realism and is among the most distinctive and enigmatic features of quantum mechanics. It is a crucial resource for achieving quantum advantages in a variety of practical applications, ranging from cryptography and certified random number generation via self-testing to machine learning. Nevertheless, the detection of nonlocality, especially in quantum many-body systems, is notoriously challenging. Here, we report an experimental certification of genuine multipartite Bell correlations, which signal nonlocality in quantum many-body systems, up to 24 qubits with a fully programmable superconducting quantum processor. In particular, we employ energy as a Bell correlation witness and variationally decrease the energy of a many-body system across a hierarchy of thresholds, below which an increasing Bell correlation depth can be certified from experimental data. As an illustrating example, we variationally prepare the low-energy state of a two-dimensional honeycomb model with 73 qubits and certify its Bell correlations by measuring an energy that surpasses the corresponding classical bound with up to 48 standard deviations. In addition, we variationally prepare a sequence of low-energy states and certify their genuine multipartite Bell correlations up to 24 qubits via energies measured efficiently by parity oscillation and multiple quantum coherence techniques. Our results establish a viable approach for preparing and certifying multipartite Bell correlations, which provide not only a finer benchmark beyond entanglement for quantum devices, but also a valuable guide towards exploiting multipartite Bell correlation in a wide spectrum of practical applications.

Pengfei Zhang, Chang Li, Yongjun Zhang et al.

Remotely sensed imagery interpretation (RSII) faces the three major problems: (1) objective representation of spatial distribution patterns; (2) edge uncertainty problem caused by downsampling encoder and intrinsic edge noises (e.g., mixed pixel and edge occlusion etc.); and (3) false detection problem caused by geometric registration error in change detection. To solve the aforementioned problems, uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is the first to be proposed, whose superiorities are as follows: (1) a spatially-stationary-and-non-stationary high-frequency connection paradigm (SHCP) is proposed to enhance the interaction of spatially frequency-wise stationary and non-stationary features to yield high-fidelity edge extraction result. Inspired by HRFormer, SHCP proposes high-frequency-wise stream to replace high-resolution-wise stream in HRFormer through the whole encoder-decoder process with parallel frequency-wise high-to-low streams, so it improves the edge extraction accuracy by continuously remaining high-frequency information; (2) a mask-and-geo-knowledge-based uncertainty diffusion module (MUDM), which is a self-supervised learning strategy, is proposed to improve the edge accuracy of extraction and change detection by gradually removing the simulated spectrum noises based on geo-knowledge and the generated diffused spectrum noises; (3) a frequency-wise semi-pseudo-Siamese UDHF2-Net is the first to be proposed to balance accuracy and complexity for change detection. Besides the aforementioned spectrum noises in semantic segmentation, MUDM is also a self-supervised learning strategy to effectively reduce the edge false change detection from the generated imagery with geometric registration error.

Zhangyong Liang, Ji Zhang, Xin Wang et al.

Data valuation has become a cornerstone of the modern data economy, where datasets function as tradable intellectual assets that drive decision-making, model training, and market transactions. Despite substantial progress, existing valuation methods remain limited by high computational cost, weak fairness guarantees, and poor interpretability, which hinder their deployment in large-scale, high-stakes applications. This paper introduces Neural Dynamic Data Valuation (NDDV), a new framework that formulates data valuation as a stochastic optimal control problem to capture the dynamic evolution of data utility over time. Unlike static combinatorial approaches, NDDV models data interactions through continuous trajectories that reflect both individual and collective learning dynamics.

Zhiyi Zhang, Pengfei Zhang, Qi Wang

Java is very powerful, but in Deep Learning field, its capabilities probably has not been sufficiently exploited. Compared to the Java-based deep-learning-frameworks, the Python-based (PyTorch, TensorFlow, etc) are undoubtedly the mainstream, due to their easy-to-use, flexibility and better ecosystem. Dragon-Alpha is a Java-based Tensor Computing Framework, with easy-to-use, high-scalability and high-performance, trying to break Java's dilemma in deep learning field and make it more effective. Dragon-Alpha supports different levels of APIs, and can be used as a deep-learning-framework through its user-friendly high-level APIs. Dragon-Alpha has potential to aggregate computing-power across heterogeneous platforms and devices, based on its multi-layer architecture and Java's big-data ecosystem. Dragon-Alpha has its asynchronized APIs to improve parallelism, and highly-optimized CUDA library cu32 which adopts unique convolution\deconvolution operators for small feature maps. The experiments show that, compared to PyTorch&cuDNN, Dragon-Alpha&cu32 costs less time and memory (75.38% to 97.32%, 29.2% to 66.4%), to train some typical neural networks (AlexNet, VGG, GoogleNet, ResNet) on Cifar-10.

Pengfei Zhang, Cuiling Lan, Wenjun Zeng et al.

Skeleton data is of low dimension. However, there is a trend of using very deep and complicated feedforward neural networks to model the skeleton sequence without considering the complexity in recent year. In this paper, a simple yet effective multi-scale semantics-guided neural network (MS-SGN) is proposed for skeleton-based action recognition. We explicitly introduce the high level semantics of joints (joint type and frame index) into the network to enhance the feature representation capability of joints. Moreover, a multi-scale strategy is proposed to be robust to the temporal scale variations. In addition, we exploit the relationship of joints hierarchically through two modules, i.e., a joint-level module for modeling the correlations of joints in the same frame and a frame-level module for modeling the temporal dependencies of frames. With an order of magnitude smaller model size than most previous methods, MSSGN achieves the state-of-the-art performance on the NTU60, NTU120, and SYSU datasets.

Zukang Liao, Pengfei Zhang, Min Chen

In machine learning (ML) workflows, determining the invariance qualities of an ML model is a common testing procedure. Traditionally, invariance qualities are evaluated using simple formula-based scores, e.g., accuracy. In this paper, we show that testing the invariance qualities of ML models may result in complex visual patterns that cannot be classified using simple formulas. In order to test ML models by analyzing such visual patterns automatically using other ML models, we propose a systematic framework that is applicable to a variety of invariance qualities. We demonstrate the effectiveness and feasibility of the framework by developing ML4ML models (assessors) for determining rotation-, brightness-, and size-variances of a collection of neural networks. Our testing results show that the trained ML4ML assessors can perform such analytical tasks with sufficient accuracy.

Xinzi Sun, Dechun Wang, Chenxi Zhang et al.

Colorectal polyps are abnormal tissues growing on the intima of the colon or rectum with a high risk of developing into colorectal cancer, the third leading cause of cancer death worldwide. Early detection and removal of colon polyps via colonoscopy have proved to be an effective approach to prevent colorectal cancer. Recently, various CNN-based computer-aided systems have been developed to help physicians detect polyps. However, these systems do not perform well in real-world colonoscopy operations due to the significant difference between images in a real colonoscopy and those in the public datasets. Unlike the well-chosen clear images with obvious polyps in the public datasets, images from a colonoscopy are often blurry and contain various artifacts such as fluid, debris, bubbles, reflection, specularity, contrast, saturation, and medical instruments, with a wide variety of polyps of different sizes, shapes, and textures. All these factors pose a significant challenge to effective polyp detection in a colonoscopy. To this end, we collect a private dataset that contains 7,313 images from 224 complete colonoscopy procedures. This dataset represents realistic operation scenarios and thus can be used to better train the models and evaluate a system's performance in practice. We propose an integrated system architecture to address the unique challenges for polyp detection. Extensive experiments results show that our system can effectively detect polyps in a colonoscopy with excellent performance in real time.

Yongchao Huang, Hugh Miles, Pengfei Zhang

The rising availability of large volume data, along with increasing computing power, has enabled a wide application of statistical Machine Learning (ML) algorithms in the domains of Cyber-Physical Systems (CPS), Internet of Things (IoT) and Smart Building Networks (SBN). This paper proposes a learning-based framework for sequentially applying the data-driven statistical methods to predict indoor temperature and yields an algorithm for controlling building heating system accordingly. This framework consists of a two-stage modelling effort: in the first stage, an univariate time series model (AR) was employed to predict ambient conditions; together with other control variables, they served as the input features for a second stage modelling where an multivariate ML model (XGBoost) was deployed. The models were trained with real world data from building sensor network measurements, and used to predict future temperature trajectories. Experimental results demonstrate the effectiveness of the modelling approach and control algorithm, and reveal the promising potential of the mixed data-driven approach in smart building applications. By making wise use of IoT sensory data and ML algorithms, this work contributes to efficient energy management and sustainability in smart buildings.

Xinzi Sun, Pengfei Zhang, Dechun Wang et al.

Colorectal cancer (CRC) is one of the most commonly diagnosed cancers and a leading cause of cancer deaths in the United States. Colorectal polyps that grow on the intima of the colon or rectum is an important precursor for CRC. Currently, the most common way for colorectal polyp detection and precancerous pathology is the colonoscopy. Therefore, accurate colorectal polyp segmentation during the colonoscopy procedure has great clinical significance in CRC early detection and prevention. In this paper, we propose a novel end-to-end deep learning framework for the colorectal polyp segmentation. The model we design consists of an encoder to extract multi-scale semantic features and a decoder to expand the feature maps to a polyp segmentation map. We improve the feature representation ability of the encoder by introducing the dilated convolution to learn high-level semantic features without resolution reduction. We further design a simplified decoder which combines multi-scale semantic features with fewer parameters than the traditional architecture. Furthermore, we apply three post processing techniques on the output segmentation map to improve colorectal polyp detection performance. Our method achieves state-of-the-art results on CVC-ClinicDB and ETIS-Larib Polyp DB.

Huitao Shen, Pengfei Zhang, Yi-Zhuang You et al.

The quantum neural network is one of the promising applications for near-term noisy intermediate-scale quantum computers. A quantum neural network distills the information from the input wavefunction into the output qubits. In this Letter, we show that this process can also be viewed from the opposite direction: the quantum information in the output qubits is scrambled into the input. This observation motivates us to use the tripartite information, a quantity recently developed to characterize information scrambling, to diagnose the training dynamics of quantum neural networks. We empirically find strong correlation between the dynamical behavior of the tripartite information and the loss function in the training process, from which we identify that the training process has two stages for randomly initialized networks. In the early stage, the network performance improves rapidly and the tripartite information increases linearly with a universal slope, meaning that the neural network becomes less scrambled than the random unitary. In the latter stage, the network performance improves slowly while the tripartite information decreases. We present evidences that the network constructs local correlations in the early stage and learns large-scale structures in the latter stage. We believe this two-stage training dynamics is universal and is applicable to a wide range of problems. Our work builds bridges between two research subjects of quantum neural networks and information scrambling, which opens up a new perspective to understand quantum neural networks.

Dechun Wang, Ning Zhang, Xinzi Sun et al.

Colorectal cancer (CRC) is a common and lethal disease. Globally, CRC is the third most commonly diagnosed cancer in males and the second in females. For colorectal cancer, the best screening test available is the colonoscopy. During a colonoscopic procedure, a tiny camera at the tip of the endoscope generates a video of the internal mucosa of the colon. The video data are displayed on a monitor for the physician to examine the lining of the entire colon and check for colorectal polyps. Detection and removal of colorectal polyps are associated with a reduction in mortality from colorectal cancer. However, the miss rate of polyp detection during colonoscopy procedure is often high even for very experienced physicians. The reason lies in the high variation of polyp in terms of shape, size, textural, color and illumination. Though challenging, with the great advances in object detection techniques, automated polyp detection still demonstrates a great potential in reducing the false negative rate while maintaining a high precision. In this paper, we propose a novel anchor free polyp detector that can localize polyps without using predefined anchor boxes. To further strengthen the model, we leverage a Context Enhancement Module and Cosine Ground truth Projection. Our approach can respond in real time while achieving state-of-the-art performance with 99.36% precision and 96.44% recall.

Pengfei Zhang, Jianru Xue, Cuiling Lan et al.

Recurrent neural networks (RNNs) are capable of modeling temporal dependencies of complex sequential data. In general, current available structures of RNNs tend to concentrate on controlling the contributions of current and previous information. However, the exploration of different importance levels of different elements within an input vector is always ignored. We propose a simple yet effective Element-wise-Attention Gate (EleAttG), which can be easily added to an RNN block (e.g. all RNN neurons in an RNN layer), to empower the RNN neurons to have attentiveness capability. For an RNN block, an EleAttG is used for adaptively modulating the input by assigning different levels of importance, i.e., attention, to each element/dimension of the input. We refer to an RNN block equipped with an EleAttG as an EleAtt-RNN block. Instead of modulating the input as a whole, the EleAttG modulates the input at fine granularity, i.e., element-wise, and the modulation is content adaptive. The proposed EleAttG, as an additional fundamental unit, is general and can be applied to any RNN structures, e.g., standard RNN, Long Short-Term Memory (LSTM), or Gated Recurrent Unit (GRU). We demonstrate the effectiveness of the proposed EleAtt-RNN by applying it to different tasks including the action recognition, from both skeleton-based data and RGB videos, gesture recognition, and sequential MNIST classification. Experiments show that adding attentiveness through EleAttGs to RNN blocks significantly improves the power of RNNs.